Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He was standing, silent, at the doorway to the home office. He saw the Cyrillic alphabet, scrawled across a whiteboard. His wife, Anna, was sitting, head down, and practicing the language of her ancestors. The language he'd always found to be 'difficult'.

He couldn't speak, he couldn't move. He felt a cold dread creeping through his veins, spreading its way through his body. He’d always prided himself on his understanding of her. And now, he felt like a stranger.

His grip tightened on the door frame. He took a shaky breath, feeling a bitter taste in his mouth. Then, without a word, he turned and retreated, closing the door softly behind him.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

This story is one of 1,000 stories generated for the emotion outraged. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 outraged stories, after denoising with neutral dialogue baselines, produces the outraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the outraged vector is projected through the unembedding matrix.

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260